Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conversion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dak
    -0.07
     Stake
    -0.06
     Gale
    -0.06
     staffers
    -0.06
     místa
    -0.06
    (pop
    -0.06
     Day
    -0.06
     Leigh
    -0.06
     fak
    -0.06
     Lud
    -0.06
    POSITIVE LOGITS
     conversion
    0.13
     converted
    0.12
     convert
    0.12
     Convert
    0.11
     Conversion
    0.11
    Convert
    0.10
    Conversion
    0.10
     conversions
    0.10
     converts
    0.09
    Converted
    0.09
    Act Density 0.028%

    No Known Activations